Skip to content
Agentmart
Submit a tool

find-cause

Use when reported wrong behavior (bug, error, crash, regression, slowdown) has no one-command repro, or its proof stays red after one plain fix attempt.

Skill by blauwtje

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying find-cause?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/blauwtje-find-cause

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when reported wrong behavior (bug, error, crash, regression, slowdown) has no one-command repro, or its proof stays red after one plain fix attempt. Not for a feature complaint.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/find-cause

What's inside

Skill name
find-cause
Description
Use when reported wrong behavior (bug, error, crash, regression, slowdown) has no one-command repro, or its proof stays red after one plain fix attempt. Not for a feature complaint.
License
MIT
Instructions
38 lines in SKILL.md · view on GitHub

Files (6)

  • SKILL.md
  • fixer-prompt.md
  • investigator-prompt.md
  • handoff.md · references/
  • loop.md · references/
  • profiling.md · references/

SKILL.md (first lines)

# Find cause

a. **Locate.** Until the cause is proven this skill outranks `spec` and `build`; a read-only planning turn writes the plan per `../spec/references/task-list.md`, reproduction test as Task 1. Worked before and one command reproduces it: run the bisect in `investigator-prompt.md` first; then run `node "${CLAUDE_SKILL_DIR}/../../lib/scratch-exclude.mjs"`; no symbol: `exo:locate-code`.
b. **Investigate.** Proven needs a causal line and a mechanism predicting it or holding in the source: write `Status: proven`; else dispatch `exo:solve-hard` from `investigator-prompt.md`.
c. **Fix.** Settle where it commits per `../build/references/workspace.md`, else copy the handoff to `.exo/debug/`. Dispatch `general-purpose` from `fixer-prompt.md`, the prompt opening with `exo-kind: build`; resume `failed` via SendMessage; if SendMessage is unavailable, dispatch a fresh agent with the prior result path.
d. **Report.** Read only status lines and Report fields. After compaction, re-run `Repro`.

1. **Reproduce.** Read an existing log, profile or `.exo/` report on the path first. One command reproduces it, else evidence, no fix.
   - Send long output to `<scratch>/debug-repro.log`, `<scratch>` from `node "${CLAUDE_SKILL_DIR}/../../lib/scratch-path.mjs" debug`; read with `tail -n 40`.
   - Steps 1-5 → read `references/loop.md` first.
2. **Instrument.**
3. **Isolate.**
4. **Predict, then fix.**
5. **Prove.**
6. **Retain project knowledge.** Per the table.
7. **Fresh eyes.** No PR review: run `node "${CLAUDE_SKILL_DIR}/../../lib/size-facts.mjs"`; when it prints `changed files` above 2 or `dependency-added yes`, or the fix crosses a public signature, persisted format or security boundary, run `code-review` at `node "${CLAUDE_SKILL_DIR}/../gate/scripts/pick-reviewer.mjs" --effort`'s level (`skip`, `low` or `medium`); fix under Step 5. End on `node "${CLAUDE_SKILL_DIR}/../route-skills/scripts/next-stage.mjs" --after find-cause --artifact none`'s output when edits to build remain; else end on `ship`.
   - Invoked by a stage or workflow: ask nothing, return to caller.

## References

| File | Read it when |
|---|---|
| `references/handoff.md` | b, c |
| `../build/references/workspace.md` | c |
| `investigator-prompt.md` | b |
| `fixer-prompt.md` | c |
| `../build/references/performance.md` | Speed |
| `references/loop.md` | 1-5 |
| `references/profiling.md` | Trace |
| `../build/references/critique.md` | No review |
| `../build/references/security.md` | When its first line applies. |
| `../build/references/data-migration.md` | When its first line applies. |
| `../build/references/test-design.md` | When its first line applies. |
| `../build/references/project-knowledge.md` | 6 |
| `../route-skills/references/closing.md` | Before the final message. |

Report: the report rule in `../route-skills/references/closing.md` with the debug log path as the pointer; mechanism, proof lines and SHAs go to the log; unproven: `Repro`, `Expected`, `Actual`, `Hypotheses`.

From blauwtje/exo, MIT.

More from blauwtje/exo

Signals

Stars
1
Forks
0
Open issues
6
Last commit (this folder)
Oct 22, 2026 (12 days ago)
Last release
Oct 19, 2026 (15 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from blauwtje

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get find-cause running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying find-cause?

CallGet help
Cite this page

find-cause skill. Agent Mart. https://agentmart.dev/skills/blauwtje-find-cause (last updated 2026-10-24)